Everything in the catalog

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*.

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically…

Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows.

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system…

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models.

Granite 4.2 8B is a dense reasoning model from IBM.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total.

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding…

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3.

Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k).

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total.

Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts).

Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts).

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes.

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes.

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka.

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net.